FFmpeg
lossless_videodsp_init.c
Go to the documentation of this file.
1 /*
2  * Lossless video DSP utils
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include "config.h"
22 #include "libavutil/x86/asm.h"
23 #include "../lossless_videodsp.h"
24 #include "libavutil/x86/cpu.h"
25 
26 void ff_add_bytes_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t w);
27 void ff_add_bytes_sse2(uint8_t *dst, uint8_t *src, ptrdiff_t w);
28 void ff_add_bytes_avx2(uint8_t *dst, uint8_t *src, ptrdiff_t w);
29 
30 void ff_add_median_pred_mmxext(uint8_t *dst, const uint8_t *top,
31  const uint8_t *diff, ptrdiff_t w,
32  int *left, int *left_top);
33 void ff_add_median_pred_sse2(uint8_t *dst, const uint8_t *top,
34  const uint8_t *diff, ptrdiff_t w,
35  int *left, int *left_top);
36 
37 int ff_add_left_pred_ssse3(uint8_t *dst, const uint8_t *src,
38  ptrdiff_t w, int left);
40  ptrdiff_t w, int left);
42  ptrdiff_t w, int left);
43 
44 int ff_add_left_pred_int16_ssse3(uint16_t *dst, const uint16_t *src, unsigned mask, ptrdiff_t w, unsigned acc);
45 int ff_add_left_pred_int16_unaligned_ssse3(uint16_t *dst, const uint16_t *src, unsigned mask, ptrdiff_t w, unsigned acc);
46 
47 void ff_add_gradient_pred_ssse3(uint8_t *src, const ptrdiff_t stride, const ptrdiff_t width);
48 void ff_add_gradient_pred_avx2(uint8_t *src, const ptrdiff_t stride, const ptrdiff_t width);
49 
50 #if HAVE_INLINE_ASM && HAVE_7REGS && ARCH_X86_32
51 static void add_median_pred_cmov(uint8_t *dst, const uint8_t *top,
52  const uint8_t *diff, ptrdiff_t w,
53  int *left, int *left_top)
54 {
55  x86_reg w2 = -w;
56  x86_reg x;
57  int l = *left & 0xff;
58  int tl = *left_top & 0xff;
59  int t;
60  __asm__ volatile (
61  "mov %7, %3 \n"
62  "1: \n"
63  "movzbl (%3, %4), %2 \n"
64  "mov %2, %k3 \n"
65  "sub %b1, %b3 \n"
66  "add %b0, %b3 \n"
67  "mov %2, %1 \n"
68  "cmp %0, %2 \n"
69  "cmovg %0, %2 \n"
70  "cmovg %1, %0 \n"
71  "cmp %k3, %0 \n"
72  "cmovg %k3, %0 \n"
73  "mov %7, %3 \n"
74  "cmp %2, %0 \n"
75  "cmovl %2, %0 \n"
76  "add (%6, %4), %b0 \n"
77  "mov %b0, (%5, %4) \n"
78  "inc %4 \n"
79  "jl 1b \n"
80  : "+&q"(l), "+&q"(tl), "=&r"(t), "=&q"(x), "+&r"(w2)
81  : "r"(dst + w), "r"(diff + w), "rm"(top + w)
82  );
83  *left = l;
84  *left_top = tl;
85 }
86 #endif
87 
89 {
91 
92 #if HAVE_INLINE_ASM && HAVE_7REGS && ARCH_X86_32
93  if (cpu_flags & AV_CPU_FLAG_CMOV)
94  c->add_median_pred = add_median_pred_cmov;
95 #endif
96 
97  if (ARCH_X86_32 && EXTERNAL_MMX(cpu_flags)) {
99  }
100 
101  if (ARCH_X86_32 && EXTERNAL_MMXEXT(cpu_flags)) {
102  /* slower than cmov version on AMD */
103  if (!(cpu_flags & AV_CPU_FLAG_3DNOW))
105  }
106 
107  if (EXTERNAL_SSE2(cpu_flags)) {
110  }
111 
112  if (EXTERNAL_SSSE3(cpu_flags)) {
116  }
117 
118  if (EXTERNAL_SSSE3_FAST(cpu_flags)) {
121  }
122 
123  if (EXTERNAL_AVX2_FAST(cpu_flags)) {
127  }
128 }
#define EXTERNAL_MMX(flags)
Definition: cpu.h:56
void ff_add_gradient_pred_ssse3(uint8_t *src, const ptrdiff_t stride, const ptrdiff_t width)
int(* add_left_pred)(uint8_t *dst, const uint8_t *src, ptrdiff_t w, int left)
int acc
Definition: yuv2rgb.c:554
int ff_add_left_pred_int16_unaligned_ssse3(uint16_t *dst, const uint16_t *src, unsigned mask, ptrdiff_t w, unsigned acc)
#define AV_CPU_FLAG_CMOV
supports cmov instruction
Definition: cpu.h:53
static atomic_int cpu_flags
Definition: cpu.c:50
#define src
Definition: vp8dsp.c:254
int ff_add_left_pred_int16_ssse3(uint16_t *dst, const uint16_t *src, unsigned mask, ptrdiff_t w, unsigned acc)
void ff_add_bytes_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t w)
uint8_t
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
void(* add_median_pred)(uint8_t *dst, const uint8_t *top, const uint8_t *diff, ptrdiff_t w, int *left, int *left_top)
#define EXTERNAL_SSE2(flags)
Definition: cpu.h:59
void ff_llviddsp_init_x86(LLVidDSPContext *c)
void(* add_gradient_pred)(uint8_t *src, const ptrdiff_t stride, const ptrdiff_t width)
void ff_add_bytes_sse2(uint8_t *dst, uint8_t *src, ptrdiff_t w)
#define EXTERNAL_AVX2_FAST(flags)
Definition: cpu.h:79
static const uint16_t mask[17]
Definition: lzw.c:38
void ff_add_median_pred_sse2(uint8_t *dst, const uint8_t *top, const uint8_t *diff, ptrdiff_t w, int *left, int *left_top)
void ff_add_gradient_pred_avx2(uint8_t *src, const ptrdiff_t stride, const ptrdiff_t width)
#define width
uint8_t w
Definition: llviddspenc.c:38
int ff_add_left_pred_unaligned_avx2(uint8_t *dst, const uint8_t *src, ptrdiff_t w, int left)
#define AV_CPU_FLAG_3DNOW
AMD 3DNOW.
Definition: cpu.h:34
int(* add_left_pred_int16)(uint16_t *dst, const uint16_t *src, unsigned mask, ptrdiff_t w, unsigned left)
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2]...the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so...,+,-,+,-,+,+,-,+,-,+,...hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32-hcoeff[1]-hcoeff[2]-...a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2}an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||.........intra?||||:Block01:yes no||||:Block02:.................||||:Block03::y DC::ref index:||||:Block04::cb DC::motion x:||||.........:cr DC::motion y:||||.................|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------------------------------|||Y subbands||Cb subbands||Cr subbands||||------||------||------|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||------||------||------||||------||------||------|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||------||------||------||||------||------||------|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||------||------||------||||------||------||------|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------------------------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction------------|\Dequantization-------------------\||Reference frames|\IDWT|--------------|Motion\|||Frame 0||Frame 1||Compensation.OBMC v-------|--------------|--------------.\------> Frame n output Frame Frame<----------------------------------/|...|-------------------Range Coder:============Binary Range Coder:-------------------The implemented range coder is an adapted version based upon"Range encoding: an algorithm for removing redundancy from a digitised message."by G.N.N.Martin.The symbols encoded by the Snow range coder are bits(0|1).The associated probabilities are not fix but change depending on the symbol mix seen so far.bit seen|new state---------+-----------------------------------------------0|256-state_transition_table[256-old_state];1|state_transition_table[old_state];state_transition_table={0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:-------------------------FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1.the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:206
#define EXTERNAL_SSSE3(flags)
Definition: cpu.h:65
int ff_add_left_pred_unaligned_ssse3(uint8_t *dst, const uint8_t *src, ptrdiff_t w, int left)
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:93
#define EXTERNAL_MMXEXT(flags)
Definition: cpu.h:57
GLint GLenum GLboolean GLsizei stride
Definition: opengl_enc.c:104
void ff_add_median_pred_mmxext(uint8_t *dst, const uint8_t *top, const uint8_t *diff, ptrdiff_t w, int *left, int *left_top)
int x86_reg
Definition: asm.h:72
static av_always_inline int diff(const uint32_t a, const uint32_t b)
int ff_add_left_pred_ssse3(uint8_t *dst, const uint8_t *src, ptrdiff_t w, int left)
void(* add_bytes)(uint8_t *dst, uint8_t *src, ptrdiff_t w)
#define EXTERNAL_SSSE3_FAST(flags)
Definition: cpu.h:66
void ff_add_bytes_avx2(uint8_t *dst, uint8_t *src, ptrdiff_t w)